figma_connect

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, openWorldHint=true and destructiveHint=false, so the mutation/external-nature bar is low. The description still adds genuinely useful context beyond them: it 'returns immediately' (non-blocking, so the agent should not expect a completed auth) and that no secrets flow through chat or tool arguments, which reassures an agent about credential handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the core action, then the non-blocking behavior, then the security property. No filler and each clause carries distinct information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-boolean setup tool with no output schema, the core mechanics are covered, but the description omits how the agent learns the flow succeeded (presumably by polling a sibling like figma_auth_status) and leaves the sole parameter undocumented. Adequate but with clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is exactly one parameter, openBrowser (boolean, default true), at 0% schema description coverage. The description never mentions it or explains what setting it to false would mean (e.g., suppress auto-opening the browser while still producing a URL). The hint about 'open a protected local panel' is too indirect to compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific action with two named modes: opening a protected local panel to save a personal Figma API token, or connecting via official OAuth. It is distinguishable from auth-lifecycle siblings like figma_auth_status and figma_disconnect, though it does not explicitly name them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: an agent can infer this is the setup step before other Figma calls, and that OAuth is an alternative to the token panel. There is no explicit when-to-use vs. figma_auth_status/figma_status guidance, no prerequisite statement, and no note on what to do once the flow completes.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.